Soft robots undergo large nonlinear spatial deformations due to both inherent actuation and external loading. The physics underlying these deformations is complex, and often requires intricate analytical and numerical models. The complexity of these models may render traditional modelbased control difficult and unsuitable. Model-free methods offer an alternative for analyzing the behavior of such complex systems without the need for elaborate modeling techniques. In this paper, we present a model-free approach for open loop position control of a soft spatial continuum arm, based on deep reinforcement learning. The continuum arm is pneumatically actuated and attains a spatial workspace by a combination of unidirectional bending and bidirectional torsional deformation. We use Deep-Q Learning with experience replay to train the system in simulation. The efficacy and robustness of the control policy obtained from the system is validated both in simulation and on the continuum arm prototype for varying external loading conditions.
Soft robots undergo large nonlinear spatial deformations due to both inherent actuation and external loading. The physics underlying these deformations is complex, and often requires intricate analytical and numerical models. The complexity of these models may render traditional model based control difficult and unsuitable. Model-free methods offer an alternative for analyzing the behavior of such complex systems without the need for elaborate modeling techniques.In this paper, we present a model-free approach for open loop position control of a soft spatial continuum arm, based on deep reinforcement learning. The continuum arm is pneumatically actuated and attains a spatial workspace by a combination ofunidirectional bending and bidirectional torsional deformation. We use Deep-Q Learning with experience replay to train the system in simulation. The efficacy and robustness of the control policy obtained from the system is validated both in simulation and on the continuum arm prototype for varying external loading conditions
Fiber reinforced elastomeric enclosures (FREEs) are soft pneumatic representative elements that can form the basis for building soft self-actuating structures/mechanisms. When placed in different configurations, they exhibit unique stroke amplification characteristics that can be leveraged to create interesting deformation patterns. Such deformations occur as a combination of axial and bending deflection due to internal pressurization and external forces. This paper presents a lumped reduced-order model that enables quick and accurate analysis of mechanisms made from FREEs grouped as a system. The model proposed is a modified four-spring pseudo-rigid-body (PRB) model that effectively captures the axial and bending stiffnesses of contracting FREEs. Parametric estimation of the model is performed using a multistart optimization routine to fit the PRB model with results from experiments and finite element analysis (FEA). The model is also generalized and statistically verified for FREEs with different fiber angles, length-to-diameter ratios, and different actuation pressures. Finally, efficacy of the approach is validated through three case studies that involve a planar arrangement of FREEs at different orientations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.